The Hormuz record.
One maintained truth object, fully inspectable. This page is assembled from the same live record our machines serve. It keeps three kinds of thing apart — what reporting says, what our own coverage measures, and what markets expect — and labels each claim with the kind of source behind it. Nothing here is retyped for marketing. When the record changes, this page changes with it.
What the record holds now
Separate layers, kept apart on purpose — reporting, our coverage metric, market expectation, our judgment, and the reporting- consensus ledger. They can disagree — and as of 2026-07-22, they do. Reading only one of them is how a machine gets this wrong.
0 · Observed operational state — primary sources, verified 2026-07-22
First-party operational issuers for the strait itself — found and verified by direct fetch on 2026-07-22. Honest label: these rows show what each issuer said as of that verification. An automated daily fetch re-verifies each source; a stamp moves only on a confirmed fetch, and a content change on the tripwire pair (UKMTO / NAVAREA IX) raises an alert for human review rather than silently refreshing. Last confirmed fetch: 2026-07-22.
1 · Observed reporting — attributed sources
What outside reporting in our tracked set says about the strait itself. Attributed, not first-party operational data — we link each source; verify at the source. Primary maritime and government feeds are the next depth (see limits below).
2 · Coverage state — our own measurement
OUR COVERAGE REGIME
fading
Our coverage of Hormuz is 29% below its 3-week baseline, sustained. This measures our attention — how much our tracked set is writing about it — not the strait's operational status.
TRACKED (OURS)
72 days
Across 10 intelligence verticals, 23 signals in the current sweep (as of 2026-07-22). Our own count.
EVENT ARC
26 markets
"Strait of Hormuz" maintained since 2026-05-24; last priced 2026-07-21.
3 · Market expectation — attributed, belief not fact
We preserve the market signal as it is: a probability stays a probability, its market stays linked, and our public calibration record measures that the signal survives our machinery without losing its meaning. Markets price collective belief about defined outcomes; they do not prove present facts. Read them for what they are: as of 2026-07-22, a return to normal is priced as unlikely in the near term, even as some transit continues.
The arc so far — deadlines passed, kept as recorded:
4 · Our reading — derived judgment
These layers disagree right now, and we do not collapse them. Our coverage of Hormuz is fading — but that measures our attention, not the strait. The reporting we hold still describes active disruption, and the markets still price a return to normal as unlikely soon. A system that read only our coverage line — or only a single fresh headline — could answer "resolved." The maintained record keeps every layer in view, so the honest answer keeps the disagreement intact: attention is down; the situation is not declared closed. This is our judgment over the layers above, labeled as such.
5 · Reporting consensus — retroactive claims ledger
What the press corpus agrees on, counted honestly: kernel facts (who, what, when, where) scored by how many independent reporting chains assert them — syndication collapsed first, so forty echoes of one wire story count once. Consensus measures reporting agreement, not reality. The “why” is frame, not fact: listed with its outlet, never averaged. This ledger is retroactive — computed 2026-07-22 over the archive our sweeps actually kept: 8 articles archived by our sweeps between 2026-06-22 and 2026-07-17 — secondary press; primary maritime and government feeds were not wired during this window.
The frames — how different outlets explain it. Attributed, never averaged; divergence here is signal, not noise.
- Financial markets have reacted positively to developments in negotiations to reopen the Strait of Hormuz. (inman)
- Investors celebrated the prospect of reopening the Strait of Hormuz. (inman)
- The oil price decline reflects the signed memorandum of understanding between the U.S. and Iran, hopefully marking the beginning of the end of the war that closed the straits of Hormuz. (realtor.com)
- Consensus measures reporting agreement, not reality — a uniformly repeated error passes any count.
- Chains are collapsed by syndication tracing; residual shared-upstream risk remains.
- Retroactive: computed 2026-07-22 over the archive, not tracked live.
- Semantic-dome membership: 43 kernel claim(s) and 5 frame(s) were source-faithful but failed typed-signature membership and are excluded — a claim enters this ledger only if its signature names a family entity (party, place, or authority) AND either its action class sits in the family's geopolitical profile or it names a family place outright.
The recorded history
Every state change is written to a ledger the moment we observe it, with how long the prior state held. The ledger records what it measured — a coverage state transition, our attention metric, not a claim about the strait. It began recording 2026-07-19; states before that date were tracked but not yet ledgered, and we say so rather than backfilling: we do not backfill history we did not record. The record is never edited after the fact.
The receipts
Every claim on this page carries the kind of source behind it, so nothing borrows more authority than it has:
- Reporting (attributed) — outside coverage, linked in layer 1; verify at the source.
- Market (attributed) — Polymarket questions, linked in layer 3; belief, not fact.
- Our own measurement — the coverage regime, tracked days, vertical and signal counts, and every ledgered transition come from our record, not an outside source.
- Derived judgment — layer 4, our reading over the layers above; ours, and labeled ours.
- Reporting consensus — layer 5, kernel facts scored by independent-chain agreement after syndication collapse; measures what the press agrees on, never reality itself.
Before and after: the answer a machine gets
This is what keeping the layers apart changes. Both columns below are built from this same record.
A SINGLE-LAYER READ RETURNS
Read only the fading coverage line and a machine answers “resolved.” Read only a stale memory of June’s peak and it answers “active closure.” One layer, one brittle verdict — and each of these is wrong in a different direction.
THE MAINTAINED RECORD RETURNS
Coverage 29% below baseline and fading (our attention); reporting still describing disruption (attributed); markets pricing a near-term return to normal as unlikely (belief) — delivered together, each with its receipt and its uncertainty. The answer: “still disrupted, attention waning, not declared resolved” — and it can cite every line.
Same subject. A more honest answer. The difference is keeping the layers apart.
The same question, read two ways
What keeping the layers apart changes for a machine reader. The left column is what a one-layer reader concludes; the right column is what the maintained record keeps in view. Each line is derived from the record’s own layers — the same truth object machines fetch — not from a staged chat.
WITHOUT THE RECORD — ONE LAYER AT A TIME
Reading only the coverage line (coverage state — our own measurement): attention is 29% below its baseline and fading — concludes “resolved — nothing happening here.”
Reading only one reporting headline (attributed): “Norway's Oil Output Beats Forecasts as Hormuz Traffic Stays Near Crisis Lows” — concludes “whatever that single frame implies — with no way to see the layers that disagree with it.”
Reading only one market price (belief, not fact): “Strait of Hormuz traffic returns to normal by July 31?” at 1% — concludes “the crowd has settled it — mistaking one question's odds for the whole state of the world.”
3 single-layer reads, 3 different verdicts — each brittle, and none aware the others exist.
WITH THE RECORD — EVERY LAYER IN VIEW
These layers disagree right now, and we do not collapse them. Our coverage of Hormuz is fading — but that measures our attention, not the strait. The reporting we hold still describes active disruption, and the markets still price a return to normal as unlikely soon. A system that read only our coverage line — or only a single fresh headline — could answer "resolved." The maintained record keeps every layer in view, so the honest answer keeps the disagreement intact: attention is down; the situation is not declared closed. This is our judgment over the layers above, labeled as such.
That is the record’s own reading — derived judgment — our reading over the layers above; ours, and labeled ours. The layers it holds apart: observed operational state · observed reporting · coverage state · market expectation · our reading · reporting consensus · the recorded history.
Provenance of this panel: each line above is derived from the record’s own layers, not from a staged chat. The coverage numbers, the headline, and the market price are fields in the same truth object served at GET /api/truth/hormuz; the right column is the record’s judgment layer, verbatim. No transcripts were invented — the disagreement is in the data.
Verify it yourself, machine or human: this exact record is served live by the API and MCP — this page, GET /api/truth/hormuz, and the get_truth_object tool are all assembled by the same builder, so what you fetch is what you are reading. One honest distinction: get_entity("hormuz") returns the broader live entity dossier — a different, complementary object, useful for trajectory and evidence receipts, but not this record.
curl -s https://signalbureau.ai/api/truth/hormuz
curl -s https://signalbureau.ai/api/mcp -X POST -H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_truth_object","arguments":{"topic":"hormuz"}}}'Honest limits
- Primary maritime and government sources are identified and verified (layer 0: UKMTO/JMIC on a 1–3 day cadence, NAVAREA IX daily). An automated daily fetch re-verifies each source; a stamp moves only on a confirmed fetch, and a content change on the tripwire pair (UKMTO / NAVAREA IX) raises an alert for human review rather than silently refreshing. Each row says which date it speaks for, and nothing updates silently.
- The coverage regime measures our declared source universe (139 actively-scraped verticals — definitions on the API page), not the whole internet, and it is our attention — not the strait's status.
- The transition ledger started 2026-07-19. Earlier state was tracked, not ledgered; we do not backfill history we did not record.
- Cadence, stated plainly: the record refreshes on a daily sweep with intraday market updates. It is maintained, not instantaneous.
- Market probabilities are collective belief about defined outcomes, never proof that an event occurred.
Informational only, never financial, legal, or investment advice. This exhibit is rebuilt from the live record on every data deploy.